Gaze Capture based Considerate Behaviour Control of Virtual Guiding Agent
Pinjung Chen, Hirnori Mitake, Shoichi Hasegawa · 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · 2022
Agents in VR have wide application like guidance. Most current agents are passive, so that people should suspend their current tasks and request agents with explicit demand. It is necessary to make agent more actively open the interaction naturally but without being bothering. We propose a virtual guidance agent which provide voice explanation in appropriate timing, using gaze tracking, attention amount estimation and attention driven state machine. We used time-decayed moving average of angle between gaze direction and face front direction. We implemented the method in VR and evaluated effectiveness in virtual guiding tour experimentally.